models
Open weights, fine-tunes and adapters. Every listing here comes live from the Hugging Face Hub, attributed to it, and links back to the source.
Qwen2.5-14B-DeepSeek-R1-1M-Uncensored-mlx-4BitQwenPhi-4-0.5b-Draft-mlx-fp16Kimi-Dev-72B-mlx-4BitLlama-3.3-70B-Instruct-abliterated-Q2-mlxQwen2.5-14B-DeepSeek-R1-1M-Uncensored-mlx-8BitMistral-Small-3.1-DRAFT-0.5B-mlx-4BitLlama-3.3-70B-Instruct-Q2-mlxDeepSeek-R1-DRAFT-Qwen2.5-Coder-0.5B-Q4-mlxDeepSeek-R1-DRAFT-Qwen2.5-Coder-0.5B-Q8-mlxOpenCodeReasoning-Nemotron-7B-mlx-8BitApriel-1.6-15b-Thinker-mlx-4BitQwenPhi-4-0.5b-Draft-mlx-4BitFoundation-Sec-8B-mlx-8BitQwQ-0.5B-Draft-mlx-4BitLlama-3.1-Nemotron-70B-Instruct-HF-Q2-mlxMellum-4b-base-mlx-fp16Rombos-LLM-V2.5-Qwen-32b-Q4-mlxApriel-1.6-15b-Thinker-mlx-8BitApriel-1.6-15b-Thinker-mlx-6BitRM-mixed-artifacts-gemma2-9b-Q4-mlxMellum-4b-sft-python-mlx-fp16cnf123Mellum-4b-sft-python-mlx-8BitLlama-3.1-Tulu-3-8B-SFT-Q4-mlxLlama-3.1-Tulu-3-8B-SFT-Q8-mlxAM-Thinking-v1-mlx-4BitCN-FinBERT-DigitCN-FinBERT-SciLight-R1-14B-DS-mlx-4Bitcogito-v1-preview-qwen-32B-mlx-3Bit